first, congratulation on spacy 3, it looks very cool !
I've read a custom pipeline for training a custom NER in spacy 2, how can I integrate that to spacy 3
here is my code in spacy 2
@plac.annotations(
model=("Model name. Defaults to blank 'en' model.", "option", "m", str),
output_dir=("Optional output directory", "option", "o", Path),
n_iter=("Number of training iterations", "option", "n", int),
)
def main(model=None, output_dir=None, n_iter=100):
"""Load the model, set up the pipeline and train the entity recognizer."""
if model is not None:
nlp = spacy.load(model) # load existing spaCy model
print("Loaded model '%s'" % model)
else:
nlp = spacy.blank("en") # create blank Language class
print("Created blank 'en' model")
# create the built-in pipeline components and add them to the pipeline
# nlp.create_pipe works for built-ins that are registered with spaCy
if "ner" not in nlp.pipe_names:
ner = nlp.create_pipe("ner")
nlp.add_pipe(ner, last=True)
# otherwise, get it so we can add labels
else:
ner = nlp.get_pipe("ner")
# add labels
for _, annotations in TRAIN_DATA:
for ent in annotations.get("entities"):
# print(f"ent {ent}")
ner.add_label(ent[2])
# get names of other pipes to disable them during training
pipe_exceptions = ["ner", "trf_wordpiecer", "trf_tok2vec"]
other_pipes = [pipe for pipe in nlp.pipe_names if pipe not in pipe_exceptions]
# only train NER
with nlp.disable_pipes(*other_pipes), warnings.catch_warnings():
# show warnings for misaligned entity spans once
warnings.filterwarnings("once", category=UserWarning, module='spacy')
# reset and initialize the weights randomly – but only if we're
# training a new model
if model is None:
nlp.begin_training()
for itn in range(n_iter):
random.shuffle(TRAIN_DATA)
losses = {}
# batch up the examples using spaCy's minibatch
batches = minibatch(TRAIN_DATA, size=compounding(4.0, 32.0, 1.001))
for batch in batches:
texts, annotations = zip(*batch)
nlp.update(
texts, # batch of texts
annotations, # batch of annotations
drop=0.5, # dropout - make it harder to memorise data
losses=losses,
)
print("Losses", losses)
# test the trained model
for text, _ in TRAIN_DATA:
doc = nlp(text)
# print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
# print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])
# save model to output directory
if output_dir is not None:
output_dir = Path(output_dir)
if not output_dir.exists():
output_dir.mkdir()
nlp.to_disk(output_dir)
print("Saved model to", output_dir)
# test the saved model
print("Loading from", output_dir)
nlp2 = spacy.load(output_dir)
# for text, _ in TRAIN_DATA:
# doc = nlp2(text)
# print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
# print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])
I understand I should use
ner = nlp.add_pipe("ner", source=source_nlp)
instead of
nlp.create_pipe("ner")
I have updated in that way, but regarding the
nlp.update
I guess there is some changes, can someone help to integrate my code to version 3?